During December 2024, this developer enhanced the GraphScope/portal repository by integrating an embedding model and refactoring the DefaultEmbedding component to inherit from EmbeddingFunction. This backend development work, implemented in Python, unified embedding usage across the portal and aligned the workflow with ChromaDB integration, improving retrieval accuracy and consistency. The refactor streamlined the text processing pipeline, increasing robustness and reducing edge-case failures in natural language processing tasks. By simplifying configuration and maintenance, the changes laid a foundation for future model updates. The work demonstrated depth in both machine learning and backend engineering, focusing on maintainability and extensibility of the embedding system.